Method for Determining Igneous Rock Mineral Content Using Element Logging Data Based on Variational AutoEncoder

Igneous rocks exhibit significant variations in mineral content due to differences in magma types and the environment in which they solidify, and the skeleton parameters of different lithology are obviously different. The determination of mineral content of the rock matrix is an important task in ev...

Full description

Saved in:
Bibliographic Details
Main Authors: JIA Ruilong, PAN Baozhi, WANG Qinghui, LI Yan, GUAN Yao, WANG Xinru
Format: Article
Language:zho
Published: Editorial Office of Well Logging Technology 2024-08-01
Series:Cejing jishu
Subjects:
Online Access:https://www.cnpcwlt.com/#/digest?ArticleID=5614
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261424502210560
author JIA Ruilong
PAN Baozhi
WANG Qinghui
LI Yan
GUAN Yao
WANG Xinru
author_facet JIA Ruilong
PAN Baozhi
WANG Qinghui
LI Yan
GUAN Yao
WANG Xinru
author_sort JIA Ruilong
collection DOAJ
description Igneous rocks exhibit significant variations in mineral content due to differences in magma types and the environment in which they solidify, and the skeleton parameters of different lithology are obviously different. The determination of mineral content of the rock matrix is an important task in evaluating reservoirs, which is of great significance in stratigraphic lithology division, calculation of matrix parameters and study of depositional environments. In this study, a predictive model for mineral content in igneous rocks is proposed. The model utilizes data from 17 elements obtained through element logging. It employs a VAE (Variational AutoEncoder) approach to predict mineral content and reconstruct the elemental weight content. The model validation reveals that the proposed model has a smaller mean absolute error and mean square error compared to three typical methods: BP (Back Propagation) neural networks, ridge regression and support vector machines. Furthermore, the model is applied to a section of buried hill igneous rock well in the South China Sea. The results demonstrate the superiority of the proposed model over the typical algorithms while maintaining good applicability.
format Article
id doaj-art-a0fb884e18754ce1bbeedfa3ce454e82
institution OA Journals
issn 1004-1338
language zho
publishDate 2024-08-01
publisher Editorial Office of Well Logging Technology
record_format Article
series Cejing jishu
spelling doaj-art-a0fb884e18754ce1bbeedfa3ce454e822025-08-20T01:55:26ZzhoEditorial Office of Well Logging TechnologyCejing jishu1004-13382024-08-0148440741510.16489/j.issn.1004-1338.2024.04.0011004-1338(2024)04-0407-09Method for Determining Igneous Rock Mineral Content Using Element Logging Data Based on Variational AutoEncoderJIA Ruilong0PAN Baozhi1WANG Qinghui2LI Yan3GUAN Yao4WANG Xinru5College of Geoexploration Science and Technology Jilin University, Changchun, Jilin 130026, ChinaCollege of Geoexploration Science and Technology Jilin University, Changchun, Jilin 130026, ChinaShenzhen Branch of CNOOC (China) LTD., Shenzhen, Guangdong 518054, ChinaCollege of Geoexploration Science and Technology Jilin University, Changchun, Jilin 130026, ChinaShenzhen Branch of CNOOC (China) LTD., Shenzhen, Guangdong 518054, ChinaCollege of Geoexploration Science and Technology Jilin University, Changchun, Jilin 130026, ChinaIgneous rocks exhibit significant variations in mineral content due to differences in magma types and the environment in which they solidify, and the skeleton parameters of different lithology are obviously different. The determination of mineral content of the rock matrix is an important task in evaluating reservoirs, which is of great significance in stratigraphic lithology division, calculation of matrix parameters and study of depositional environments. In this study, a predictive model for mineral content in igneous rocks is proposed. The model utilizes data from 17 elements obtained through element logging. It employs a VAE (Variational AutoEncoder) approach to predict mineral content and reconstruct the elemental weight content. The model validation reveals that the proposed model has a smaller mean absolute error and mean square error compared to three typical methods: BP (Back Propagation) neural networks, ridge regression and support vector machines. Furthermore, the model is applied to a section of buried hill igneous rock well in the South China Sea. The results demonstrate the superiority of the proposed model over the typical algorithms while maintaining good applicability.https://www.cnpcwlt.com/#/digest?ArticleID=5614igneous rockmineral contentvae (variational autoencoder)element logging
spellingShingle JIA Ruilong
PAN Baozhi
WANG Qinghui
LI Yan
GUAN Yao
WANG Xinru
Method for Determining Igneous Rock Mineral Content Using Element Logging Data Based on Variational AutoEncoder
Cejing jishu
igneous rock
mineral content
vae (variational autoencoder)
element logging
title Method for Determining Igneous Rock Mineral Content Using Element Logging Data Based on Variational AutoEncoder
title_full Method for Determining Igneous Rock Mineral Content Using Element Logging Data Based on Variational AutoEncoder
title_fullStr Method for Determining Igneous Rock Mineral Content Using Element Logging Data Based on Variational AutoEncoder
title_full_unstemmed Method for Determining Igneous Rock Mineral Content Using Element Logging Data Based on Variational AutoEncoder
title_short Method for Determining Igneous Rock Mineral Content Using Element Logging Data Based on Variational AutoEncoder
title_sort method for determining igneous rock mineral content using element logging data based on variational autoencoder
topic igneous rock
mineral content
vae (variational autoencoder)
element logging
url https://www.cnpcwlt.com/#/digest?ArticleID=5614
work_keys_str_mv AT jiaruilong methodfordeterminingigneousrockmineralcontentusingelementloggingdatabasedonvariationalautoencoder
AT panbaozhi methodfordeterminingigneousrockmineralcontentusingelementloggingdatabasedonvariationalautoencoder
AT wangqinghui methodfordeterminingigneousrockmineralcontentusingelementloggingdatabasedonvariationalautoencoder
AT liyan methodfordeterminingigneousrockmineralcontentusingelementloggingdatabasedonvariationalautoencoder
AT guanyao methodfordeterminingigneousrockmineralcontentusingelementloggingdatabasedonvariationalautoencoder
AT wangxinru methodfordeterminingigneousrockmineralcontentusingelementloggingdatabasedonvariationalautoencoder